Multivariate Time Series Classification Using Spiking Neural Networks
Multivariate Time Series Classification Using Spiking Neural Networks
复制标题
DOI：
10.1109/ijcnn48605.2020.9206751
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Haowen Fang;Amar Shrestha;Qinru Qiu
中科院分区：
文献类型：
--
作者：
Haowen Fang;Amar Shrestha;Qinru Qiu
在物联网（IoT）和网络物理系统（CPS）的发展和扩展的驱动下，在诸如嵌入式设备之类的能量受限场景中，对处理时态数据流的需求日益增加。尖峰神经网络引起了人们的关注，因为它通过将信息编码和处理为稀疏尖峰事件来实现低功耗，这可以用于事件驱动的计算。最近的工作也显示了SNN处理时空信息的能力。功率受限的设备可以利用这些优点来处理实时传感器数据。然而，大多数现有的SNN训练算法集中在视觉任务和时间信用分配没有解决。此外，目前广泛采用的码率编码忽略了时间信息，不适合表示时间序列。在这项工作中，我们提出了一个编码方案，将时间序列转换为稀疏的时空尖峰模式。提出了一种时空模式分类的训练算法。在UCR存储库中的多个时间序列数据集上评估了所提出的方法，并实现了与深度神经网络相当的性能。
There is an increasing demand to process streams of temporal data in energy-limited scenarios such as embedded devices, driven by the advancement and expansion of Internet of Things (IoT) and Cyber-Physical Systems (CPS). Spiking neural network has drawn attention as it enables low power consumption by encoding and processing information as sparse spike events, which can be exploited for event-driven computation. Recent works also show SNNs’ capability to process spatial temporal information. Such advantages can be exploited by power-limited devices to process real-time sensor data. However, most existing SNN training algorithms focus on vision tasks and temporal credit assignment is not addressed. Furthermore, widely adopted rate encoding ignores temporal information, hence it’s not suitable for representing time series. In this work, we present an encoding scheme to convert time series into sparse spatial temporal spike patterns. A training algorithm to classify spatial temporal patterns is also proposed. Proposed approach is evaluated on multiple time series datasets in the UCR repository and achieved performance comparable to deep neural networks.